You can deploy this model and start earning money today!

RichardErkhov/
MaziyarPanahi_-_Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1-gguf

Name: MaziyarPanahi_-_Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1 - GGUF

Model creator: https://huggingface.co/MaziyarPanahi/
Original model: https://huggingface.co/MaziyarPanahi/Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1/

Name	Quant method	Size
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q2_K.gguf	Q2_K	2.53GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.IQ3_XS.gguf	IQ3_XS	2.81GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.IQ3_S.gguf	IQ3_S	2.96GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q3_K_S.gguf	Q3_K_S	2.95GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.IQ3_M.gguf	IQ3_M	3.06GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q3_K.gguf	Q3_K	3.28GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q3_K_M.gguf	Q3_K_M	3.28GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q3_K_L.gguf	Q3_K_L	3.56GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.IQ4_XS.gguf	IQ4_XS	3.67GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q4_0.gguf	Q4_0	3.83GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.IQ4_NL.gguf	IQ4_NL	3.87GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q4_K_S.gguf	Q4_K_S	3.86GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q4_K.gguf	Q4_K	4.07GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q4_K_M.gguf	Q4_K_M	4.07GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q4_1.gguf	Q4_1	4.24GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q5_0.gguf	Q5_0	4.65GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q5_K_S.gguf	Q5_K_S	4.65GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q5_K.gguf	Q5_K	4.78GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q5_K_M.gguf	Q5_K_M	4.78GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q5_1.gguf	Q5_1	5.07GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q6_K.gguf	Q6_K	5.53GB
Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags:

Safetensors
mistral
text-generation-inference
merge
mistral
7b
mistralai/Mistral-7B-Instruct-v0.1
NousResearch/Yarn-Mistral-7b-64k
transformers
pytorch
mistral
text-generation
custom_code
en
dataset:emozilla/yarn-train-tokenized-16k-mistral
arxiv:2309.00071
license:apache-2.0
autotrain_compatible
endpoints_compatible
has_space
text-generation-inference
region:us

Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1

Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1 is a merge of the following models:

🧩 Configuration

yaml

slices:
  - sources:
      - model: mistralai/Mistral-7B-Instruct-v0.1
        layer_range: [0, 32]
      - model: NousResearch/Yarn-Mistral-7b-64k
        layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-Instruct-v0.1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "MaziyarPanahi/Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

RichardErkhov/MaziyarPanahi_-_Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1-gguf

Original model description:

Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1

🧩 Configuration

💻 Usage

RichardErkhov/
MaziyarPanahi_-_Yarn-Mistral-7b-64k-Mistral-7B-Instruct-v0.1-gguf